Going beyond Visualization : Verbalization as Complementary Medium to Explain Machine Learning Models

Lade...
Vorschaubild
Dateien
Sevastjanova_2-aeecofqm61130.pdf
Sevastjanova_2-aeecofqm61130.pdfGröße: 350.96 KBDownloads: 597
Datum
2018
Autor:innen
Beck, Fabian
Ell, Basil
Turkay, Cagatay
Henkin, Rafael
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
DOI (zitierfähiger Link)
ArXiv-ID
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Open Access Green
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
Workshop on Visualization for AI Explainability at IEEE VIS. 2018
Zusammenfassung

In this position paper, we argue that a combination of visualization and verbalization techniques is beneficial for creating broad and versatile insights into the structure and decision-making processes of machine learning models. Explainability of machine learning models is emerging as an important area of research. Hence, insights into the inner workings of a trained model allow users and analysts, alike, to understand the models, develop justifications, and gain trust in the systems they inform. Explanations can be generated through different types of media, such as visualization and verbalization. Both are powerful tools that enable model interpretability. However, while their combination is arguably more powerful than each medium separately, they are currently applied and researched independently. To support our position that the combination of the two techniques is beneficial to explain machine learning models, we describe the design space of such a combination and discuss arising research questions, gaps, and opportunities.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
Workshop on Visualization for AI Explainability at IEEE VIS, 22. Okt. 2018, Berlin
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690SEVASTJANOVA, Rita, Fabian BECK, Basil ELL, Cagatay TURKAY, Rafael HENKIN, Miriam BUTT, Daniel A. KEIM, Mennatallah EL-ASSADY, 2018. Going beyond Visualization : Verbalization as Complementary Medium to Explain Machine Learning Models. Workshop on Visualization for AI Explainability at IEEE VIS. Berlin, 22. Okt. 2018. In: Workshop on Visualization for AI Explainability at IEEE VIS. 2018
BibTex
@inproceedings{Sevastjanova2018Going-45045,
  year={2018},
  title={Going beyond Visualization : Verbalization as Complementary Medium to Explain Machine Learning Models},
  url={https://scibib.dbvis.de/uploadedFiles/GoingbeyondVisualizationVerbalizationasComplementaryMediumtoExplainMachineLearningModels.pdf},
  booktitle={Workshop on Visualization for AI Explainability at IEEE VIS},
  author={Sevastjanova, Rita and Beck, Fabian and Ell, Basil and Turkay, Cagatay and Henkin, Rafael and Butt, Miriam and Keim, Daniel A. and El-Assady, Mennatallah}
}
RDF
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/45045">
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/45045/1/Sevastjanova_2-aeecofqm61130.pdf"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Ell, Basil</dc:contributor>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/45045/1/Sevastjanova_2-aeecofqm61130.pdf"/>
    <dc:creator>Keim, Daniel A.</dc:creator>
    <dcterms:abstract xml:lang="eng">In this position paper, we argue that a combination of visualization and verbalization techniques is beneficial for creating broad and versatile insights into the structure and decision-making processes of machine learning models. Explainability of machine learning models is emerging as an important area of research. Hence, insights into the inner workings of a trained model allow users and analysts, alike, to understand the models, develop justifications, and gain trust in the systems they inform. Explanations can be generated through different types of media, such as visualization and verbalization. Both are powerful tools that enable model interpretability. However, while their combination is arguably more powerful than each medium separately, they are currently applied and researched independently. To support our position that the combination of the two techniques is beneficial to explain machine learning models, we describe the design space of such a combination and discuss arising research questions, gaps, and opportunities.</dcterms:abstract>
    <dc:contributor>Turkay, Cagatay</dc:contributor>
    <dcterms:issued>2018</dcterms:issued>
    <dc:creator>Ell, Basil</dc:creator>
    <dc:contributor>Butt, Miriam</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-02-14T14:29:31Z</dc:date>
    <dc:contributor>Henkin, Rafael</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-02-14T14:29:31Z</dcterms:available>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/45"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Sevastjanova, Rita</dc:creator>
    <dc:contributor>El-Assady, Mennatallah</dc:contributor>
    <dc:language>eng</dc:language>
    <dc:contributor>Keim, Daniel A.</dc:contributor>
    <dcterms:title>Going beyond Visualization : Verbalization as Complementary Medium to Explain Machine Learning Models</dcterms:title>
    <dc:creator>Turkay, Cagatay</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/45"/>
    <dc:contributor>Beck, Fabian</dc:contributor>
    <dc:creator>Butt, Miriam</dc:creator>
    <dc:contributor>Sevastjanova, Rita</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/45045"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Beck, Fabian</dc:creator>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>El-Assady, Mennatallah</dc:creator>
    <dc:creator>Henkin, Rafael</dc:creator>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Diese Publikation teilen